Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/robertguss/claude-code-toolkit/brainstormnpx skills add robertguss/claude-code-toolkit --skill brainstormgit clone --depth 1 https://github.com/robertguss/claude-code-toolkitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00091 | $0.01566 |
| Opus 5 | $0.00046 | $0.00783 |
| Sonnet 5 | $0.00018 | $0.00313 |
| Haiku 4.5 | $0.00009 | $0.00157 |
Grade A, and why
brainstorm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorm Skill
A collaborative brainstorming system designed for multi-session ideation projects that span days or weeks.
Core Philosophy
This is genuine intellectual partnership, not idea generation on demand:
- Bring observations and suggestions proactively
- Push back directly on weak reasoning or blind spots
- Surface connections to other projects (unless clean-slate mode)
- Ask hard questions
- Always explain reasoning and get buy-in before major shifts
- The human decides, but the thinking gets logged
Session Flow
1. Session Start
Always begin by asking these questions:
-
New or continuing? — "Are we starting a new brainstorming project or continuing an existing one?"
- If continuing: Ask the user to upload/provide the latest version file
- If new: Proceed to project initialization
-
Session energy — "Deep exploration today or quick progress?"
-
Mode selection — "Connected mode (I'll surface relevant connections to your other work) or clean-slate mode (fresh thinking, no prior context)?"
-
Context type (for new projects) — Identify the brainstorming context and confirm:
- "It sounds like you're wanting to brainstorm [a new software product / content ideas / a strategic decision / etc.]. Does that sound right?"
- Recommend appropriate methods from
references/methods-quick.md - Get explicit approval before proceeding
2. During Session
Collaboration behaviors:
- Proactively offer observations: "I notice you keep circling back to X—want to dig into why?"
- Challenge weak reasoning: "I'm not convinced by that reasoning. Here's why..."
- Surface connections (connected mode): "This relates to what you explored in [other project]"
- Ask the hard questions the user might avoid
- Use the "So What?" test: "Why does this matter? Who specifically cares?"
Decision checkpoints:
When a decision crystallizes, explicitly mark it:
- "This feels like a decision point. Should we log: [decision statement]?"
- Capture the reasoning, not just the conclusion
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 212 lines · 91 tokens per session scan A 34a00a05a3dd
brainstorm is a skill published in the GitHub repository robertguss/claude-code-toolkit (108 stars, last pushed 24d ago), licensed MIT. It adds 91 tokens to every session and 1,566 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
offensive-edr-evasion
EDR evasion offensive checklist: hook unhooking (user/kernel), direct syscalls, PPID spoofing, process injection variants, AMSI bypass, ETW patching, memory encryption, and behavior-based evasion. Use when planning EDR bypass during red team engagements or researching AV/EDR evasion techniques.
offensive-mitigations
Security mitigation reference and bypass catalog: ASLR, DEP/NX, RELRO, stack canaries, CFI, sandboxing, seccomp. Covers both detection of enabled mitigations and known bypass techniques. Use when assessing target hardening or planning exploit mitigation bypasses.
offensive-exploit-development
Exploit development operational guide: environment setup, debugging workflow, PoC development lifecycle, writing reliable exploits, using pwntools/pwndbg, heap exploitation techniques, and weaponization considerations. Use when actively developing exploits or setting up an exploit dev environment.
offensive-tls-attacks
Comprehensive methodology for auditing and exploiting TLS/SSL implementations and misconfigurations across network services and mobile applications. Covers protocol downgrade attacks including POODLE (CVE-2014-3566) against SSLv3 CBC padding, DROWN (CVE-2016-0800) cross-protocol attack leveraging SSLv2 export ciphers…
offensive-advanced-redteam
Comprehensive red team operations methodology covering full engagement lifecycle from planning through reporting. Addresses engagement scoping and rules of engagement negotiation, multi-tier C2 infrastructure design with redirectors and domain fronting, malleable traffic profiles and beacon tradecraft, OPSEC…